{"id":"W2538750502","doi":"10.1109/iembs.2004.1403077","title":"Respiratory sounds classification using cepstral analysis and Gaussian mixture models","year":2005,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Mel-frequency cepstrum; Pattern recognition (psychology); Speech recognition; Vector quantization; Mixture model; Computer science; Artificial intelligence; Multilayer perceptron; Feature vector; Perceptron; Feature extraction; Cepstrum; Hidden Markov model; Artificial neural network; Support vector machine; Gaussian","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001799902,0.00009074312,0.0001182598,0.0001772586,0.0001697892,0.0002623885,0.0002255468,0.00006091583,0.00002190469],"category_scores_gemma":[0.00000389907,0.00007600407,0.000047981,0.0006540692,0.00003877859,0.0009876055,0.00006316778,0.00007852626,0.000003399421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003234047,"about_ca_system_score_gemma":0.00005117648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001759495,"about_ca_topic_score_gemma":0.00003939402,"domain_scores_codex":[0.9991583,0.00002800653,0.0001621192,0.0003221686,0.0001586084,0.000170787],"domain_scores_gemma":[0.9995108,0.00001274565,0.00007313808,0.000284939,0.00003909077,0.00007924895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001098903,0.0001675414,0.01663998,0.00006410993,0.0003976871,0.00001031876,0.005431938,0.03797472,0.04746578,0.3106214,0.002449868,0.5787656],"study_design_scores_gemma":[0.00008445913,0.000006171516,0.005157669,0.000005014382,0.00004564012,0.000002891753,0.00003330517,0.9898628,0.0009845846,0.00269055,0.0009991438,0.0001277972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09190713,0.0001397758,0.9000948,0.001177948,0.0000243969,0.00002935536,3.883791e-7,0.00007770259,0.006548502],"genre_scores_gemma":[0.8539089,0.000002731615,0.1443163,0.001423716,0.00008615918,0.00000117274,7.090447e-7,0.000003408793,0.0002568734],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9518881,"threshold_uncertainty_score":0.3099356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06297010440452305,"score_gpt":0.2887242472730468,"score_spread":0.2257541428685237,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}